Seal Imprint Recognition with Joint Transform Correlators

摘要

IN many commercial applications in Chinese society, seals instead of signatures for person identification are widely used, such as money withdrawing lists, checks, receipts, etc. It needs high rate of correctness. However, it can not be effective if the process of safety validation is inspected merely by human eyes. Also, for safe control and management, in addition to the potential human cheating act, there is also a possible error due to human neglect. Based on the constrained energy minimization joint transform correlator (CEMJTC), we have proposed a prototype Chinese seal recognition system, which combines the advantage of light speed and programmability of computer. The CEM filter designed for optical correlator has the desirable property of sharp peak with low sidelobes levels in the output correlation plane. The major advantages of the system are alignment simplicity, rotation invariant capability, high discrimination capability and suitability for hybrid optical signal processing.